{
 "id": "TurkuNLP/finerweb-10bt",
 "owner": "TurkuNLP",
 "name": "finerweb-10bt",
 "downloads": 114,
 "likes": 8,
 "last_modified": "2025-01-17T13:54:02.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{henriksson2025finerweb10btrefiningwebdata,\n      title={FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering}, \n      author={Erik Henriksson and Otto Tarkka and Filip Ginter},\n      year={2025},\n      eprint={2501.07314},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2501.07314}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "af4776a675231d96e6c7aeba7138229044202089",
 "stated_evidence": "https://huggingface.co/datasets/TurkuNLP/finerweb-10bt/blob/af4776a675231d96e6c7aeba7138229044202089/README.md",
 "file_evidence": "https://huggingface.co/datasets/TurkuNLP/finerweb-10bt/tree/af4776a675231d96e6c7aeba7138229044202089",
 "card_nc": false
}